Loading...
Loading...
Found 345 Skills
Initializes and maintains architecture artifacts with handoff-first context loading, lazy scoped updates, and compact JSON handoff output for workflow-driven invocations.
AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.
Create and maintain AI coding agent subagents (.claude/agents/*.md, .codex/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.
Executes the implementation plan from a specification. Loops through plan phases, delegates tasks to specialists, updates phase status on completion. Supports resuming from partially-completed plans.
Coordinate Claude Code Agent Teams through filesystem-based protocol. Use when orchestrating multiple Claude agents on parallel tasks, need task dependency management, multi-agent code review or implementation. Do not use when single-agent work suffices, task is not parallelizable.
Autonomous coding agent. Delegate any task that involves understanding, writing, or running code — from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.
Team-orchestrated implement → verify → fix → archive cycle
Orchestrates parallel KB generation using spatial analysis and a map-reduce architecture with incremental update support.
Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, managing agent teams, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agent team", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.
Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
Durable asynchronous messaging channel for inter-agent communication. Implements write-once read-many filesystem mail using atomic writes and directory-based mailboxes.
Standalone squad manager — creates, inspects, validates, and manages squads (multi-agent teams). Scaffolds directories, agents, tasks, workflows. Registers squads for slash commands. Works independently without AIOS. Activates on: create squad, list squads, add agent, validate squad, run workflow, inspect squad, manage squad.